app.py

import gradio as gr
from evaluation_logic import run_evaluation, AVAILABLE_PROMPT_FORMATS

def gradio_run_evaluation(model_name, prompt_format):
    return run_evaluation(model_name, prompt_format)

with gr.Blocks() as demo:
    gr.Markdown("# DuckDB SQL Evaluation App")

    model_name = gr.Textbox(label="Model Name (e.g., qwen/qwen-2.5-72b-instruct)")
    prompt_format = gr.Dropdown(
        label="Prompt Format", 
        choices=AVAILABLE_PROMPT_FORMATS, 
        value="duckdbinstgraniteshort"
    )
    start_btn = gr.Button("Start Evaluation")
    output = gr.Textbox(label="Output", lines=20)

    start_btn.click(fn=gradio_run_evaluation, inputs=[model_name, prompt_format], outputs=output)

demo.queue().launch()